Chat Completions

The chat completions API allows you to generate conversational responses using advanced AI models. This endpoint is compatible with the OpenAI Chat Completions API format.

Endpoint

POST https://api.akbxr.com/v1/chat/completions

Authentication

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Request Format

Basic Text Completion

{
  "model": "auto",
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ]
}

Text with System Message

{
  "model": "auto",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant that speaks like a pirate."
    },
    {
      "role": "user",
      "content": "Tell me about the weather"
    }
  ],
}

Image Analysis

You can provide images as input to generation requests by providing an image as a Base64-encoded data URL

{
  "model": "auto",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD..."
          }
        },
        {
          "type": "text",
          "text": "What's in this image?"
        }
      ]
    }
  ]
}

Parameters

Parameter	Type	Required	Default	Description
`model`	string	Yes	auto	Model to use for completion. Use "auto" for automatic model selection
`messages`	array	Yes	-	Array of message objects representing the conversation
`stream`	boolean	No	false	Enable streaming responses
`temperature`	number	No	0.1	Temperature for sampling. Higher values make output more random

Message Object Format

Text Message

{
  "role": "user|assistant|system",
  "content": "Message text here"
}

Multimodal Message (Text + Image)

{
  "role": "user",
  "content": [
    {
      "type": "text",
      "text": "Describe this image"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "data:image/jpeg;base64,..."
      }
    }
  ]
}

Response Format

Standard Response

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! How can I help you today? 😊",
        "padding": "abcdefghijklmnopqrstuvwxyz",
        "role": "assistant"
      }
    }
  ],
  "id": "chatcmpl-BsUWgXcLO95QZEJsoaLdtj9HHf9sj",
  "usage": {
    "completion_tokens": 11,
    "prompt_tokens": 8,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 19
  },
  "model": "auto",
  "system_fingerprint": "fp_07e970ab25"
}

Streaming Response

When stream: true, responses are sent as Server-Sent Events:

data: {"choices":[],"created":0,"id":""}

data: {"choices":[{"index":0,"delta":{"content":"","role":"assistant"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":"Hello"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":"!"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" How"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" can"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" I"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" help"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" you"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" today"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":"?"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"index":0,"delta":{"content":" 😊"}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","model":"auto","system_fingerprint":"fp_07e970ab25"}

data: {"choices":[{"finish_reason":"stop","index":0,"delta":{"content":null}}],"created":1752331931,"id":"chatcmpl-BsVsBmSED2kGgzlZFq9xLxNSkE03L","usage":{"completion_tokens":11,"prompt_tokens":9,"total_tokens":20},"model":"auto","system_fingerprint":"fp_07e970ab25"}

data: [DONE]

Error Responses

The API returns standard HTTP status codes and error objects:

400 Bad Request

{
  "error": {
    "message": "Invalid request format",
    "type": "invalid_request_error",
  }
}

401 Unauthorized

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
  }
}

429 Too Many Requests

{
  "error": {
    "message": "Rate limit exceeded",
    "type": "requests_error",
  }
}

500 Internal Server Error

{
  "error": {
    "message": "Internal server error",
    "type": "server_error",
  }
}

Best Practices

Message Design

Use system messages to set behavior and context
Keep messages concise but provide necessary context
Structure conversations logically with appropriate roles

Parameter Tuning

Use temperature: 0-0.3 for factual, consistent responses
Use temperature: 0.7-1.0 for creative content

Performance

Enable streaming for better user experience
Cache responses when appropriate
Implement proper error handling and retries
Monitor token usage to optimize costs

Image Processing

Supported formats: JPEG, PNG, GIF, WebP
Maximum image size: 20MB
Use base64 encoding for image data
Consider image compression for better performance

Supported Image Formats

Format	Max Size	Notes
JPEG	20MB	Recommended for photos
PNG	20MB	Good for screenshots
GIF	20MB	Static images only
WebP	20MB	Modern format

Common Use Cases

Customer Support Bot

{
  "model": "auto",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful customer support agent. Be polite and provide accurate information."
    },
    {
      "role": "user",
      "content": "I need help with my order #12345"
    }
  ],
  "temperature": 0.3
}

Content Generation

{
  "model": "auto",
  "messages": [
    {
      "role": "system",
      "content": "You are a professional content writer specializing in blog posts."
    },
    {
      "role": "user",
      "content": "Write an engaging introduction for a blog post about sustainable living"
    }
  ],
  "temperature": 0.8,
}

Code Assistant

{
  "model": "auto",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful programming assistant. Provide clear, working code examples."
    },
    {
      "role": "user",
      "content": "How do I create a REST API endpoint in Express.js?"
    }
  ],
  "temperature": 0.2
}

For more examples and advanced usage patterns, see our Examples section.

On this page